Region Normalization for Image Inpainting

Authors: Tao Yu, Zongyu Guo, Xin Jin, Shilin Wu, Zhibo Chen, Weiping Li, Zhizheng Zhang, Sen Liu12733-12740

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that our method outperforms current state-of-the-art methods quantitatively and qualitatively.
Researcher Affiliation Academia CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, University of Science and Technology of China {yutao666, guozy, jinxustc, shilinwu, zhizheng}@mail.ustc.edu.cn, {chenzhibo, wpli}@ustc.edu.cn, elsen@iat.ustc.edu.cn
Pseudocode No The paper does not contain structured pseudocode or explicitly labeled algorithm blocks.
Open Source Code Yes 1The codes are available at https://github.com/geekyutao/RN
Open Datasets Yes We evaluate our methods on Places2 (Zhou et al. 2017) and Celeb A (Liu et al. 2015) datasets.
Dataset Splits No The paper mentions testing on 'total validation data (36500 images) of Places2' but does not provide explicit train/validation/test dataset splits (e.g., percentages or counts) for the datasets used.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes We set threshold t = 0.8 in this work. We apply RN-B in the early layers (encoder) of our generator and RN-L in the intermediate and later layers (the residual blocks and decoder).